Spend the Bits Where the Tiny Objects Are: Rate-Utility Region Coding for Aerial Detection

Yanliang Qi; Jiacheng Ding; Cong Guo; Peihua Mai

cs.CVNov 1, 2026

Spend the Bits Where the Tiny Objects Are: Rate-Utility Region Coding for Aerial Detection

Authors: Yanliang Qi, Jiacheng Ding, Cong Guo, Peihua Mai

Organizations: University of Memphis · National University of Singapore

Abstract

Bandwidth-limited aerial cameras must compress their images before a remote detector can find the many tiny objects in them. Threshold-based region-of-interest (ROI) coding sends only confidently detected regions, and because tiny objects provide limited visual evidence and often score low, it can discard the regions that contain them. We propose rate-utility region coding (RUO), which sends a region when its expected detection utility justifies its measured byte cost, choosing to drop it or to send it at low or high quality with one multiplier shared across images. RUO trains no model, uses a standard image codec and decodes in a few milliseconds. On all 1,610 VisDrone-DET test-dev images, RUO uses 42.4% fewer bits than a tuned threshold-based ROI coder, averaged over their shared tiny-object average precision (AP) range. RUO also needs fewer bits for tiny objects than the AV1 Image File Format (AVIF), High Efficiency Video Coding (HEVC) and three published learned codecs, and its advantage over threshold-based ROI coding persists when the sender and receiver use different detectors. For AP over all object sizes RUO needs 25.4% more bits than the tuned ROI coder, because its allocation drops large regions first at low rates, so it suits tasks that target tiny objects. We plan to release the code.

Figures & tables

Figure 2: RUO workflow with frozen sender

E

and receiver

D

: calibrated utility and measured byte costs guide a shared-

\lambda

choice of drop, low or high quality; selected regions are decoded for detection.

Figure 3: Recall decomposition on VisDrone test-dev with sender and receiver D1, showing the outcome of every tiny ground-truth object at each method’s operating point closest to 0.2 bpp, actual rate in brackets (top), and the share of objects of area

\geq 32^{2}

that are selection misses against rate (bottom).

sender D1
RUO versus	AP tiny BD-rate	AP BD-rate
ROI-P. tuned	$\mathbf{-42.4}$	$+25.4$
ROI-P. $\tau{=}0.25$	$-52.3$	$+24.1$
ROI-P. small only	$-19.6$	$-14.0$
AVIF	$-77.3$	$-24.9$
HEVC intra, x265	$-74.9$	$-32.1$

Table 1: BD-rate (%) of RUO on all 1,610 VisDrone test-dev images , receiver D1 with sliced inference, where a negative value means fewer bits than the baseline for the same AP and bold highlights the tuned ROI comparisons (95% CIs in Tab. S4 of the supplementary material).

Figure 4: Rate–accuracy on VisDrone test-dev for tiny objects (left) and all sizes (right) with sender and receiver D1, each curve the Pareto envelope of a method’s operating points and the dotted line the uncompressed images.

§ One usable rate, AP tiny 9.33 at 0.165 bpp, where RUO reaches 9.82; RUO reaches 9.33 at 0.150 bpp.
Codec (published weights)	vs AVIF	RUO vs codec
mbt2018-mean [ 31 ]	$-28.5$	$\mathbf{-44.0}$
cheng2020-anchor [ 8 ]	$-35.0$	$\mathbf{-39.5}$
TransTIC base [ 7 ]	$-22.7$	$\mathbf{-48.4}$
Adapt-ICMH [ 26 ]	$-20.5$	$\mathbf{-50.1}$
SA-ICM [ 34 ] §	–	–

Table 2: Learned codecs with published weights, AP tiny BD-rate (%) on the 200 development images with receiver D1, on intervals where no curve has a bpp gap above 2

\times

, with bold marking the RUO-versus-codec column.

VisDrone test-dev, sender D1
Comparison	AP tiny	AP
small only vs tuned ROI-P.	$-27.5$ [-33.2, -17.6]	$+223.8$ [+87.2, +318.2]
same, sender D2	$-26.1$ [-33.2, -18.6]	$+165.1$ [+86.8, +277.4]
tuned ROI-P. vs AVIF	$-50.5$ [-59.4, -27.1]	$-34.4$ [-41.9, -21.3]
Test-dev, RUO vs tuned ROI-P., BD-AP (points)
sender D1 / D2	$+1.17$ / $+1.20$	$-1.08$ / $-0.96$

Table 3: Further results , BD-rate (%) for AP tiny and AP over all sizes unless a block states another unit, with 95% CIs over scenes where they were computed.

Figure 5: Qualitative examples illustrating RUO’s tiny-object detection advantage at approximately 0.2 bpp. From left to right: original with tiny ground truth (GT), AVIF, ROI-Packing-lite+ (ROI-P+), and our rate-utility region coding (RUO). Each row is a different image, shown as the fixed 512 $\times$ 384-pixel crop. True positives are teal, false positives amber dotted, missed tiny objects coral dashed, and transmitted regions white (dotted for low quality). Pale grayscale context in the last two columns is untransmitted and provides spatial reference only. Actual full-image bpp in AVIF/ROI-P+/RUO order: (a) 0.183/0.207/0.193; (b) 0.185/0.209/0.200; (c) 0.190/0.191/0.207.

Variant	sender D1	sender D2
RUO, fixed tier weight (final)	$\mathbf{-28.7}$	$\mathbf{-23.8}$
RUO-M, measured detectability utility	$-20.3$	$-11.7$
raw score instead of calibrated	$-17.6$	$-12.0^{\dagger}$
two tiers (drop / high)	$-16.5$	$-7.8$
plus low-resolution base layer	$-16.0$	$-6.9$
All regions on one canvas, one AVIF image	$-8.6$	$+1.2$

Table 4: Ablations : AP tiny BD-rate (%) against tuned ROI-Packing-lite+ on the 200 development images with receiver D1 unless stated, where bold marks the frozen method and indented rows change one component of RUO-M.

Figure 6: Failure cases of region selection at approximately 0.2 bpp, with columns and markings as in Fig. 5 . Actual full-image bpp in AVIF/ROI-P+/RUO order: (a) 0.198/0.219/0.196; (b) 0.200/0.192/0.199.

Method	bpp	enc.	dec.	recv.	GPU MB
RUO (ours)	0.191	340 ∗	7.9	73	688
ROI-Packing-lite+	0.198	175 ∗	8.6	79	688
AVIF	0.159	103	18.1	129	688
JPEG	0.197	18	15.5	170	688
mbt2018-mean	0.165	67	91.9	100	1056
TransTIC base	0.158	172	204.0	99	9573

Table 5: Latency in ms, the median over 21 fixed test-dev images with 5 synchronized runs each, and peak GPU memory on an NVIDIA RTX 6000 Ada Generation, where ∗ marks encoding times that include the sender detector and the receiver runs sliced inference on the decoded image.

Region codec	vs ROI-P.	vs full frame	vs ROI-P., AP
AVIF (main paper)	-28.7	–	+1.2
JPEG	-25.4	-65.6	+28.9
WebP	-8.9	-52.1	+27.5

Table S1 : Region codec , RUO’s BD-rate (%) on the 200 development images with sender and receiver D1 when every region and every baseline uses the given codec, all within the 2

\times

bpp-gap rule.

Setting	value	AP tiny	AP
frozen	–	-28.7	+1.2
tier weight $w_{\text{lo}}$ (0.6)	0.3	-22.8	+42.0
	0.9	-15.5	-8.8
low quality $q_{\text{lo}}$ (35)	20	-19.2	+6.2
	50	-22.8	+42.0
high quality $q_{\text{hi}}$ (65)	50	-49.4	+14.5

Table S2 : Sensitivity , BD-rate (%) of RUO with one setting changed against tuned ROI-Packing-lite+ on the development set with sender and receiver D1, with bpp gaps of at most 1.7

\times

in the AP tiny comparison.

	AP tiny at bpp			AP at bpp
Method	0.10	0.20	0.25	0.10	0.20	0.25
RUO (ours)	6.20	7.63	7.76	16.09	20.12	20.95
ROI-P. tuned	4.81	6.63	7.17	18.74	20.67	21.07
ROI-P. $\tau{=}0.25$	4.54	5.84	6.19	18.54	20.16	20.49
AVIF	2.18	4.58	5.25	13.62	18.34	19.61
JPEG	–	2.19	2.73	–	13.11	14.48

Table S3 : AP tiny and AP (%) at fixed rates on test-dev with sender and receiver D1, where ROI-P. is ROI-Packing-lite+, bold marks the best deployable tiny AP and the uncompressed images reach AP tiny 8.72 and AP 22.92.

sender D1
RUO versus	AP tiny BD-rate	AP BD-rate
ROI-P. tuned	$\mathbf{-42.4}$ [-55.1, -26.6]	$+25.4$ [+15.9, +37.3]
ROI-P. $\tau{=}0.25$	$-52.3$ [-69.4, -38.1]	$+24.1$ [+12.6, +41.5]
ROI-P. small only	$-19.6$ [-36.9, +0.2]	$-14.0$ [-18.4, -6.2]
AVIF	$-77.3$ [-83.4, -66.2]	$-24.9$ [-37.7, -4.1]
HEVC intra, x265	$-74.9$ [-82.4, -60.8]	$-32.1$ [-45.2, -7.2]

Table S4 : BD-rate (%) of RUO on all 1,610 VisDrone test-dev images with 95% CIs , receiver D1 with sliced inference, where a negative value means fewer bits than the baseline for the same AP, brackets give the CI over 61 scenes and bold highlights the tuned ROI comparisons.

Protocol	Sender	RUO vs	AP tiny	AP	Official AP
Validation calibration,	UAVDT model	ROI-P. tuned	$-41.2$ [-64.5, -9.0]	$+8.8$ [-16.8, +44.9]	$+27.2$
20 test sequences		AVIF	$-71.8$ [-87.0, -41.7]	$-33.9$ [-62.7, +20.4]	$-34.8$
	VisDrone D1	ROI-P. tuned	$-6.5$ [-48.5, +17.8]	$+17.1$ [-12.8, +67.6]	$+43.6$
		AVIF	$-63.6$ [-82.6, -22.3]	$+5.6$ [-33.6, +77.2]	$+12.5$
Earlier, test calibration,	UAVDT model	ROI-P. tuned	$-16.5$ [-52.1, +33.7]	$+13.3$ [-13.6, +52.0]	–
15 test sequences		AVIF	$-64.1$ [-79.9, -37.7]	$-29.4$ [-63.4, +10.9]	–

Table S5 : UAVDT , BD-rate (%) of RUO with receiver UAVDT-YOLOv8m and 95% CIs over sequences, under the main paper’s protocol (top, 20 test sequences, 1,667 frames) and the earlier one (bottom, 15 sequences, 1264 frames), with the official toolkit’s class-agnostic AP as a point estimate.

bpp	images	W/L	$p_{\text{ROI-P.}}$	$p_{\text{AVIF}}$	RUO	ROI-P.	AVIF
0.1	232	55/68	0.28	0.009	30.9	32.2	31.4
0.2	284	83/78	0.75	0.005	34.7	36.0	32.9
0.3	115	44/29	0.10	0.032	40.2	39.0	38.4

Table S6 : Per-image tiny-object recall on test-dev with sender D1 and each method within 10% of the target rate per image, with W/L the images where RUO’s recall is higher or lower than that of threshold coding (ROI-P.),

p

the two-sided sign test against ROI-P. and AVIF, and mean recall in %.

#	bpp	tiny	ref.	RUO	strongest		ROI-P.	AVIF
1	0.1	30	10	14	x265	9	7	4
2	0.2	19	15	14	x265	12	10	10
3	0.2	21	9	10	ROI-P.	8	8	4
4	0.1	33	17	16	ROI-P.	13	13	10
5	0.2	23	13	14	ROI-P.	12	12	8
6	0.2	23	11	11	TransTIC	9	1	9

Table S7 : Images where RUO gains most over the strongest of seven baselines at approximately matched per-image rates on test-dev with sender and receiver D1, counting tiny objects found at IoU 0.5 with the class label and score

\geq 0.05

, with ref. the count on the uncompressed frame and strongest the baseline that finds most tiny objects on that image.

Panel of Figure 18 — Figure S1 : Ranks 1 and 4 of Tab. S7 at 0.1 bpp, each method at its own point closest to the target on that image, with boxes drawn on the original frame zoomed on the $480\times 270$ window with the most tiny objects, detected tiny objects in teal, false positives with score $\geq 0.05$ in amber dotted and missed tiny objects in coral dashed.

Figure S2 : The teaser image , at the 90th percentile of tiny-object count, with AVIF at 0.190 bpp finding 10/79 tiny objects, threshold coding at 0.191 bpp finding 18/79 and RUO at 0.207 bpp finding 27/79, against 43/79 on the uncompressed frame.

Figure S3 : Median image by tiny-object count, from left to right the original with its tiny ground truth, AVIF, threshold coding (ROI-Packing-lite+) and RUO, each at its point closest to 0.2 bpp on this image.

Figure S4 : 10th-percentile image by tiny-object count, in the layout of Fig. S3 .

Figure S5 : First failure case , an image where no method finds any tiny object at about 0.2 bpp, in the layout of Fig. S3 .

Task-Aware Compression

See all 16 papers

DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery
Apr 14, 2026Yann V. BellecSmall Object Detection Aerial Object Detection
TERA: Task-Evidence Restoration for Underwater Object Detection under Bandwidth-Constrained Transmission
Nov 2, 2026Heejin Kim, Joon-Seok Song, Eunil ParkUnderwater Object Detection Object Detection
Sungkyunkwan University, Seoul, Republic of Korea · Jaume I University, Castellon, Spain
HGSQ: Heatmap-Guided Sparse Query Detector for Real-Time Aerial Small Object Detection
Sep 10, 2026Yangchen ZengObject Detection Aerial Object Detection
School of Cyber Science and Engineering, Southeast University, Nanjing, 211189, China.

Apr 14, 2026J/K move · Enter open · S save

DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery

Yann V. Bellec

Small Object Detection Aerial Object Detection Efficient Object Detection Structured Pruning

Open paper AskPDF arXiv

Aerial object detection in UAV imagery presents unique challenges due to the high prevalence of tiny objects, adverse environmental conditions, and strict computational constraints. Standard YOLO-based detectors fail to address these jointly: their minimum detection stride of 8 pixels renders sub-32px objects nearly undetectable, their CIoU loss produces zero gradients for non-overlapping tiny boxes, and their architectures contain significant filter redundancy. We propose DroneScan-YOLO, a holistic system contribution that addresses these limitations through four coordinated design choices: (1) increased input resolution of 1280x1280 to maximize spatial detail for tiny objects, (2) RPA-Block, a dynamic filter pruning mechanism based on lazy cosine-similarity updates with a 10-epoch warm-up period, (3) MSFD, a lightweight P2 detection branch at stride 4 adding only 114,592 parameters (+1.1%), and (4) SAL-NWD, a hybrid loss combining Normalized Wasserstein Distance with size-adaptive CIoU weighting, integrated into YOLOv8's TaskAligned assignment pipeline. Evaluated on VisDrone2019-DET, DroneScan-YOLO achieves 55.3% mAP@50 and 35.6% mAP@50-95, outperforming the YOLOv8s baseline by +16.6 and +12.3 points respectively, improving recall from 0.374 to 0.518, and maintaining 96.7 FPS inference speed with only +4.1% parameters. Gains are most pronounced on tiny object classes: bicycle AP@50 improves from 0.114 to 0.328 (+187%), and awning-tricycle from 0.156 to 0.237 (+52%).

Abstract

Task-Aware Compression

Explore similar work

DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery

TERA: Task-Evidence Restoration for Underwater Object Detection under Bandwidth-Constrained Transmission

HGSQ: Heatmap-Guided Sparse Query Detector for Real-Time Aerial Small Object Detection