arXiv:2606. 01973v1 Announce Type: new Abstract: Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes.
The paper investigates how evaluation protocols and ground‑truth quality affect the classification performance of Multimodal Large Language Models (MLLMs). It identifies and corrects key issues such as discarded out‑of‑list outputs, inflated distractor choices, and poor open‑world mapping, and shows that design choices like batch size, image ordering, and text encoder selection significantly influence accuracy. Using a multilabel reannotation of 625 ImageNet‑1k classes (ReGT), the study finds that corrected labels can boost MLLM performance by up to 10.8%, narrowing the gap with supervised models, and demonstrates that MLLMs can assist human annotators in about half of difficult cases.
arXiv:2607. 16283v1 Announce Type: cross Abstract: The rapid advancement of generative AI has outpaced our ability to reliably detect its outputs, particularly when detectors encounter generators they have not seen before.
arXiv:2607. 06254v1 Announce Type: cross Abstract: Deepfake image detection is currently served by three fundamentally different paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors.
The study evaluates 16 AI‑generated image detection methods in a zero‑shot setting, testing 23 pretrained variants on 12 datasets with 2.6 million images from 291 generators. Results show no single detector consistently outperforms others, with accuracy ranging from 37.5 % to 75.0 %. The study highlights that training data alignment and generator type significantly affect performance, especially against modern commercial models, and identifies systematic failure patterns across datasets.
PairCLIP‑SWA is a single‑backbone deepfake detector that fine‑tunes an OpenCLIP ViT‑L/14 visual tower using a class‑balanced corpus created by CLIP‑similarity‑guided subsampling and then applies stochastic weight averaging over the fine‑tuning trajectory. Trained on the IEEE SP Cup 2025 (DF‑Wild‑Cup) benchmark, the weight‑averaged model achieves 97.04 % accuracy, 98.64 % AU‑ROC and a 4.07 % equal error rate—outperforming the best published three‑backbone ensemble. The study shows that averaging stabilizes validation performance, prevents misranking on disjoint test sets, and that CLIP pre‑training, rather than ensembling, is the key driver of accuracy.
arXiv:2608. 15802v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection remains challenging for image classifiers, especially when near-OOD samples lie close to in-distribution (ID) class boundaries.
Out-of-distribution (OOD) detection remains challenging for image classifiers, especially when near-OOD samples lie close to in-distribution (ID) class boundaries. Recent vision-language detectors imp...
arXiv:2506.04713v4 Announce Type: replace Abstract: A key challenge in Few-Shot Recognition (FSR) is the scarcity of labeled task-specific data for training. Contemporary methods mitigate this challe...
arXiv:2410.21582v4 Announce Type: replace-cross Abstract: Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of mainta...
arXiv:2606. 24178v1 Announce Type: cross Abstract: Pretrained vision models often misclassify inputs that are rotated, scaled, or sheared, even though these affine transformations leave the object class unchanged.
arXiv:2610.27211v1 Announce Type: new Abstract: Continual vision-language models (VLMs) encounter a stream of environments and must also reject inputs that do not belong to the environment at hand....