Vision-language models (VLMs) deployed on consumer hardware must decide when to answer and when to defer, and that decision depends on having a confidence signal that tracks correctness. A practitioner with a fixed memory budget faces a choice between a small model at full precision, the same small model quantized, and a larger model quantized into the same footprint -- three configurations that push the confidence signal in opposing directions. We measure, on identical inputs, how model scale and 4-bit quantization affect two confidence signals in the Qwen2-VL family: the confidence a model states in natural language, and its own mean token probability over the answer it generates. Across 5,700 predictions spanning six realistic photographic degradations at three severities, we find that scale sharply improves the model's internal uncertainty signal (mean error-detection AUROC 0.80 to 0.98 from 2B to 7B) while its verbalized confidence stays weak and often at chance (mean 0.61 to 0.69): the gap between what the model knows and what it says widens rather than closes with size. We find that 4-bit quantization is nearly free for accuracy (-1.6 points) but expensive for the confidence signal (internal AUROC 0.95 to 0.80, and the verbalized-confidence parse rate collapses from 99% to 64%). For a fixed memory budget the recommendation is therefore to prefer a larger quantized model over a smaller full-precision one: 7B-4bit gives both the best accuracy and the best uncertainty signal (internal AUROC 0.98) of the three configurations that fit. We frame the results as selective-prediction operating points so they translate directly into a deployment recommendation, and we argue that error-detection AUROC, not calibration error, is the metric that exposes the difference between the two signals.
Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting. In such settings, a reliable uncertainty signal matters more than raw accuracy, because it determines when a system should defer rather than answer. We evaluate two small open-weight VLMs -- Qwen2-VL-2B-Instruct and SmolVLM-Instruct -- across six realistic photographic degradations at three severity levels, comparing two confidence signals: the confidence the model states in natural language, and the model's own mean token probability over its generated answer. Across 3,800 predictions, we find a large and consistent gap. Verbalized confidence in Qwen2-VL is almost constant (mean 0.87-0.90 across all conditions) and detects its own errors at chance level (AUROC 0.39-0.75, typically ~0.50), while internal token probability from the same model separates correct from incorrect answers with AUROC 0.92-0.99. In SmolVLM, verbalized confidence proved largely unobtainable: across three prompt templates, only one of five pilot attempts produced a parseable confidence value, while internal probability again yielded above-chance error detection (AUROC 0.54-0.92). Both models fail in the same place: under severe underexposure, accuracy collapses (0.99->0.22 for Qwen2-VL, 0.97->0.42 for SmolVLM) while both confidence signals barely move, and internal error-detection falls to chance. We conclude that small VLMs encode usable self-knowledge that their verbalized output does not express, that internal probability is therefore the better deferral signal in constrained deployment, and that neither signal should be trusted under severe low-light conditions.
Medical image segmentation models often report high benchmark accuracy under ideal imaging conditions, yet their failures under clinical degradation can be quiet: sensor noise, patient motion, low- resolution acquisition, and contrast variability may all alter model behavior without producing an obvious warning. We present a reproducible framework for evaluating uncertainty-aware segmentation under con- trolled clinical degradation. Our experiments use a synthetic multimodal brain tumor MRI cohort generated with a biophysical phantom simulator that follows the BraTS protocol. We train U-Net and Attention U-Net baselines for multi-class tumor sub-region segmentation and augment both models with Monte Carlo dropout to estimate per-voxel uncertainty. Across eight clinically motivated corruption types at five severity levels, we measure segmentation accuracy, calibration, failure detection, and selective prediction coverage. On clean data, Attention U-Net achieves a whole-tumor Dice of 0.990; under severe Gaussian noise, its performance falls to 0.089. Predictive uncertainty rises with degradation and tracks segmentation error (Pearson r = 0.53 under severity-3 Gaussian noise), allowing us to flag failures with an AUROC of 0.843. These results argue for uncertainty-aware inference as a practical safety layer in physician-in-the-loop radiology workflows. We release the code, trained models, and evaluation protocol to support direct reproduction.
Segment Anything Model (SAM) has revolutionized promptable image segmentation with strong zero-shot generalization. However, its performance degrades substantially under real-world imaging artifacts such as noise, blur, and compression. Existing methods restore features globally without focusing on segmentation-relevant regions and neglect SAM's iterative refinement mechanism, leading to suboptimal performance in interactive settings. We propose Prompt-Guided Feature Enhancement SAM (PGE-SAM), a framework that explicitly leverages user prompts and prior mask predictions to spatially guide the feature restoration process toward regions of interest through a Prompt Guidance Generator. To recover fine-grained details lost under degradation, we introduce Multi-Scale Features Interaction to incorporate low-level encoder features, along with a Foreground Reconstruction Loss that restricts feature-level supervision to the segmentation target. Furthermore, we present DM-Seg, a benchmark for interactive segmentation on degraded medical images, spanning multiple imaging modalities with both general and modality-specific degradations at varying severity levels. Extensive experiments demonstrate that PGE-SAM achieves SOTA robustness on both medical and natural image domains across multiple degradation levels, while maintaining generalization to clean images and adding less than one-fifth of the parameters of prior methods.
Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight image degradation. In addition to weaker degradations that can accidentally occur in the image processing pipeline, there is another risk of malicious deepfakes that specifically introduce degradations, purposefully exploiting the detector's weaknesses in that regard. Here, we present an overview of the NTIRE 2026 Robust Deepfake Detection Challenge, which specifically addresses that problem. Participants were tasked with building a detector that would later be tested on an unknown test-set, which included both common and uncommon degradations of various strengths. With a total number of 337 participants and 57 submissions to the final leaderboard, the first edition of the challenge was well received. To ensure the reliability of the results, participants were given only 24h to complete the test run with no labels provided, limiting the possibility of training on the test data. Furthermore, the top solutions were scored on a private test-set to detect any such overfitting. This report presents the competition setting, dataset preparation, as well as details and performance of methods. Top methods rely on large foundation models, ensembles, and degradation training to combine generality and robustness.