Introduces COVD task and Novel-114 benchmark plus NoIn-Det, a parameter-free method that freezes the visual encoder and updates limited text parameters to inject novel concepts while preserving old knowledge.
F-vlm: Open-vocabulary object detection upon frozen vision and language models
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
fields
cs.CV 8verdicts
UNVERDICTED 8representative citing papers
ExDet proposes a lightweight framework using text-guided extrapolation, detector-compatible rectification, and recalibrated proposals to achieve state-of-the-art open-domain open-vocabulary detection on multiple benchmarks.
CL-CLIP uses CLIP image-text cost volumes to create class-specific pathways processed by a multi-expert RoI head, improving continual object detection on VOC and COCO over the F-ViT baseline.
A new framework improves open-vocabulary object detection on novel categories by using scene graphs for relational modeling and distilling knowledge from image captions.
The authors define the LV-OSD problem and introduce the LVDor dual-branch framework with TPDW dynamic weighting and PRM masking to align multimodal prompts for open-set detection.
CLIP-RD adds VRD for cross-modality distillation consistency and XRD for bidirectional cross-modal symmetry to align student embedding geometry more closely with the teacher, yielding a 0.8 percentage point gain over prior distillation methods.
ViTs exhibit lazy aggregation by relying on irrelevant background patches for global semantics, and selectively integrating patch features into the CLS token reduces this effect and improves results across label-, text-, and self-supervision.
ForgeryGPT integrates a forgery localization expert and mask encoder into an LLM for pixel-level forgery detection, localization, and explainable output via three-stage training on custom mask-text and instruction datasets.
citing papers explorer
-
COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
Introduces COVD task and Novel-114 benchmark plus NoIn-Det, a parameter-free method that freezes the visual encoder and updates limited text parameters to inject novel concepts while preserving old knowledge.
-
ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification
ExDet proposes a lightweight framework using text-guided extrapolation, detector-compatible rectification, and recalibrated proposals to achieve state-of-the-art open-domain open-vocabulary detection on multiple benchmarks.
-
CL-CLIP: CLIP-Based Continual Learning Framework with Cost-Volume Category Decoupling for Object Detection
CL-CLIP uses CLIP image-text cost volumes to create class-specific pathways processed by a multi-expert RoI head, improving continual object detection on VOC and COCO over the F-ViT baseline.
-
Unveiling the Unknown: Open Vocabulary Object Detection with Scene Graphs
A new framework improves open-vocabulary object detection on novel categories by using scene graphs for relational modeling and distilling knowledge from image captions.
-
LV-OSD: Language-Vision-Complementary Open-Set Object Detection
The authors define the LV-OSD problem and introduce the LVDor dual-branch framework with TPDW dynamic weighting and PRM masking to align multimodal prompts for open-set detection.
-
CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation
CLIP-RD adds VRD for cross-modality distillation consistency and XRD for bidirectional cross-modal symmetry to align student embedding geometry more closely with the teacher, yielding a 0.8 percentage point gain over prior distillation methods.
-
Vision Transformers Need More Than Registers
ViTs exhibit lazy aggregation by relying on irrelevant background patches for global semantics, and selectively integrating patch features into the CLS token reduces this effect and improves results across label-, text-, and self-supervision.
-
ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization
ForgeryGPT integrates a forgery localization expert and mask encoder into an LLM for pixel-level forgery detection, localization, and explainable output via three-stage training on custom mask-text and instruction datasets.