Paintseg: Painting pixels for training-free segmentation
The paper introduces PaintSeg, a new unsupervised method for segmenting objects without
any training. We propose an adversarial masked contrastive painting (AMCP) process …
any training. We propose an adversarial masked contrastive painting (AMCP) process …
QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition
Audiovisual segmentation (AVS) is a challenging task that aims to segment visual objects in
videos according to their associated acoustic cues. With multiple sound sources and …
videos according to their associated acoustic cues. With multiple sound sources and …
PaintSeg: training-free segmentation via painting
The paper introduces PaintSeg, a new unsupervised method for segmenting objects without
any training. We propose an adversarial masked contrastive painting (AMCP) process …
any training. We propose an adversarial masked contrastive painting (AMCP) process …
A closer look at reinforcement learning-based automatic speech recognition
Reinforcement learning (RL) has demonstrated effectiveness in improving model
performance and robustness for automatic speech recognition (ASR) tasks. Researchers …
performance and robustness for automatic speech recognition (ASR) tasks. Researchers …
-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations
Referring perception, which aims at grounding visual objects with multimodal referring
guidance, is essential for bridging the gap between humans, who provide instructions, and …
guidance, is essential for bridging the gap between humans, who provide instructions, and …
Part-aware Personalized Segment Anything Model for Patient-Specific Segmentation
Precision medicine, such as patient-adaptive treatments utilizing medical images, poses
new challenges for image segmentation algorithms due to (1) the large variability across …
new challenges for image segmentation algorithms due to (1) the large variability across …
Training-free CryoET Tomogram Segmentation
Cryogenic Electron Tomography (CryoET) is a useful imaging technology in structural
biology that is hindered by its need for manual annotations, especially in particle picking …
biology that is hindered by its need for manual annotations, especially in particle picking …
[PDF][PDF] R 2-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations
X Li, K Qiu, J Wang, X Xu, R Singh, K Yamazaki… - CoRR, 2024 - researchgate.net
Referring perception, which aims at grounding visual objects with multimodal referring
guidance, is essential for bridging the gap between humans, who provide instructions, and …
guidance, is essential for bridging the gap between humans, who provide instructions, and …