- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
The paper suggest an approach to fuse features from frozen Vision Transformer (Dinov3) with CNN backbone to benefit from global infromation lacking in CNN backbones for object detection. Path features of Dinov3 are reshaped to have same resolution of last block of their CNN feature extractor (C5) and aslo number of channels are increased to match those of C5. After concatenation of featues conv 1x1 is applied which brings the fused feature block to same dimension as C5 which removes the need to make any adjustment for susequent layers. Through empirical studies, they demonstrate performance gain for CNN object detectors (both 1 and 2 stage CNN object detectors) on PASCAL-VOC, Palm Oil and COCO when fusing the features with frozen Dinov3.
Critical strengths
- Clear presentation of idea
- Strong empirical results covering 2 object detectors and 3 datasets.
- Ablation studies to further study the impact of feature fusion (impact of datasets and number of training labels)
Critical weaknesses
-
Lack of novelty: While this paper for the first time suggest feature fusion of Dinov3 with CNN backbone for object detection but similar fusion of frozen ViT with CNN can be found in prior works:
-
Lack of justification for the proposed design: comapring CNN + Dinov3 (frozne) with fine-tuning of DInov3 we observe that fine-tuned Dinov3 has better performance while less total parameters. The only benefit of CNN + DINOV3 (frozen) is lower trainbale parameters which comes at cost of lower performance compared to Dinov3 fine tuning.
-
Missing ablation: despite having diverse experiments which are appreciated but there is no study showing that after training how much information is carried from C5 and how much from Dinov3.
Questions for authors
-
Based on table 4c, fine-tuning of Dinov3 results in better performance with lower total parameters at the cost of more trainable parameters. Therefore, benefit of CNN + frozen Dinov3 is limited to only efficiency in training phase?
-
The idea of fusing frozen vision transformer with CNN network can be traced back at prior works such as:
Zhi Cai, Yingjie Gao, Yanan Zhang, Xinzhu Ma, and Di Huang. “Towards Unbiased Source-Free Object Detection via Vision Foundation Models.” Pattern Recognition, 2026, article 113545
Xiangyu Gao, Yu Dai, Benliu Qiu, Lanxiao Wang, Heqian Qiu, and Hongliang Li. “Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection.
While your idea is not identical what fundemental novelty separates your work from prior works.