Search Results for author:
Found 5 papers, 1 papers with code
Anchor-based Robust Finetuning of Vision-Language Models
Specifically, two types of anchors are elaborated in our method, including i) text-compensated anchor which uses the images from the finetune set but enriches the text supervision from a pretrained captioner, ii) image-text-pair anchor which is retrieved from the dataset similar to pretraining data of CLIP according to the downstream task, associating with the original CLIP text with rich semantics.
VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding
Extensive experiments on four dense scene understanding tasks demonstrate the superiority of VMT-Adapter(-Lite), achieving a 3. 96%(1. 34%) relative improvement compared to single-task full fine-tuning, while utilizing merely ~1% (0. 36%) trainable parameters of the pre-trained model.
HODN: Disentangling Human-Object Feature for HOI Detection
However, these methods ignore the relationship among humans, objects, and interactions: 1) human features are more contributive than object ones to interaction prediction; 2) interactive information disturbs the detection of objects but helps human detection.
Distributed Attention for Grounded Image Captioning
We study the problem of weakly supervised grounded image captioning.
Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
Weakly supervised object localization(WSOL) remains an open problem given the deficiency of finding object extent information using a classification network.
