- Rating
- 1(−1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper shows that standard black-box occlusion saliency (RISE/D-RISE) fails on VLMs for two reasons. Tight masks get read as objects ("the cat has black eyes"), and probability weights saturate on a confident model, so the D-RISE map is almost exactly a count of how often each pixel was kept. The proposed SAM-RISE ablates around 30 SAM regions as grey bounding boxes, scores changes in the logit margin, and keeps both positive and negative evidence. When log-probabilities aren't available, it estimates them from 20 sampled answers. Experiments cover pointing and insertion on COCO and ImageNet, a comparison with Grad-CAM and rollout, a negative-evidence correction on NaturalBench (Qwen3-VL, Gemma 4), class-level population maps on ImageNet, and a small run on Gemini.
Critical strengths
The diagnosis in Section 3 is the most useful part for me. Showing that VLMs re-interpret tight masks as content, and that D-RISE's published estimator collapses to the mask-count field (correlation 0.9994), is a clean and practical warning. Anyone running occlusion probes on VLMs should know this, whatever happens to the method itself.
I also appreciate that the paper is honest about where it loses. It openly says random masks win given hundreds of queries, and that the Grad-CAM comparison and the user study use selected examples.
Critical weaknesses
- The gains are modest relative to how they're framed. The "negative evidence is actionable" claim rests on a +0.2 joint-accuracy change on Qwen (not significant) and +1.5 on Gemma, with a true-positive cost, about 32 extra calls per question, and a damping exponent (k = 5) that is needed for it to help at all. I wonder whether a much cheaper baseline, like a global bias shift toward "no" or simple recalibration of P(yes), would get similar true-negative gains. Without that comparison I can't tell whether the region-level signal matters, or whether it's just lowering yes-confidence overall.
- The evaluation doesn't quite match the method's own argument. Section 3 argues the bounding box is the right occluder, but the pointing benchmark uses the mask-shaped occluder. The advantage over D-RISE holds only below about 75–100 queries. The white-box comparison and the human study (14 showcase pairs, 11 raters) are on selected examples, and the Gemini evidence is 5 pairs. Each piece is reasonable alone, but together the evidence for "SAM-RISE is the better tool" feels thinner than the paper suggests. It reads more like a strong diagnosis paper with a reasonable method attached.
Questions for authors
- Does the NaturalBench gain survive against a simple calibration baseline (a global shift or threshold tuned on held-out data)? This would most directly change my assessment.
- Why does the pointing benchmark use the mask-shaped occluder instead of the bounding box? What are the numbers with the bbox?
- The bbox covers about 1.55× the mask area. You mention a dilated-outline control and a matched-area random-box null as future work. Could you run at least a small version? Right now the "signal tracks the part, not the context" claim is only correlational.
- For the population maps, how sensitive are the results to the choice of query image that seeds the anchors? Only 10 classes are covered.
A minor thing is, relational questions seem to fail (Fig. 10). How often does this happen on NaturalBench overall?
2 comments
W2 / Q2. The pointing benchmark used the mask occluder; what are the bounding-box numbers? We reran the benchmark with the bounding-box occluder on the same 500 COCO and 500 ImageNet images, with the same SAM regions, model, prompt and call budget. Only the shape of the hidden region changes.
| Pointing game | Mask occluder (paper) | Box occluder | p (McNemar) |
|---|---|---|---|
| ImageNet, GT box | 0.796 | 0.654 | 9e-10 |
| COCO, GT box | 0.802 | 0.594 | 2e-16 |
| COCO, GT mask | 0.726 | 0.438 | 4e-26 |
Boxes lose 14 to 29 points, and on ImageNet they fall below the image-centre control (0.704). The two operators serve different purposes, and the revision states which one is used where. The box is the right operator for measuring a region's effect: it removes the re-interpretation failure of Sec. 3 and doubles the deep-drop tail. The mask is the right operator for localising. A box of a large or elongated region also hides neighbouring content, often the object itself, so a background region can inherit the object's score drop and win the argmax. We see the same effect in App. I, where a background box can span the whole frame. A box also hides about 1.6× the mask's pixels, so this run changes shape and area together, and the dilated-outline control (Q3) separates the two. With area-normalised scoring, boxes do better than masks (e.g. 0.566 vs 0.480 on COCO, GT box), but both stay far below the headline scoring. The revised Table 6 reports both occluders. On the budget crossover we agree, and the paper says so. SAM-RISE wins per query below about 75 to 100 calls, the regime a paid API imposes, and random masks win given hundreds. On SAM-RISE's own regions and budget, LIME ties SAM-RISE (0.740 vs 0.726 PG, p = 0.52), while KernelSHAP and PixelSHAP are worse. With 2 to 4 times the queries, LIME and SHAP pass SAM-RISE by 3 to 5 points.
Closed models and the 5 Gemini pairs. SAM-RISE needs only the model's answers, so it applies to any model unchanged. We are running it on two more closed models from two more providers, Claude Fable 5.1 (Anthropic) and GPT-6 Astra (OpenAI), and extending Gemini 3.8 Flash from 5 to all 16 image-question pairs. All use the unchanged pipeline (same SAM regions, prompt, grey boxes and 20 sampled answers). Each is scored quantitatively with the metric of Sec. 6.3: is the region that flips Qwen's log-probability answer among the model's top regions? We will include these results in the revised paper.
Selected examples. The white-box and user-study comparisons are now labelled illustrative in the main text. The quantitative claims rest on the 500 + 500-image benchmark, the matched-budget LIME/SHAP/PixelSHAP comparison, and NaturalBench on two models.
Q3. Dilated outline and matched-area random box. We agree that the current evidence is correlational (within box-area deciles, a box's background fraction does not predict its effect; Spearman 0.03 over 66,018 boxes). We are running the causal version: for each SAM region, the bounding box, the outline dilated to the box's area, and a random box of the same size placed off the region, compared paired on the same images. We will include the results in the revised paper.
Q4. Sensitivity of population maps to the query image. We are rerunning the population study with several query images per class and on more classes. We will report the spread of the class-averaged drop across query images and whether the separation between recognised and language-prior classes holds, and include the results in the revised paper.
Q5. How often do relational questions fail? We measured this on NaturalBench (Qwen3-VL, the 534 groups with SAM masks, 1,578 yes/no items). For each item, we checked whether removing any single SAM region as a grey box flips the answer. A flipping region exists for 42.7% of items, and for the other 57% no single region is decisive. Questions with relational or counting words are not worse than the rest (44.7% vs 41.7% have a flipping region). The limit is the single-region probe in general, not relations in particular, and the revised limitations section reports this.
We thank the reviewer for the careful reading, and for crediting the diagnosis and the paper's candour about where SAM-RISE loses.
W1 / Q1. Does the NaturalBench gain survive a calibration baseline? We ran the controls the reviewer suggests on the stored scores, with no new queries. NaturalBench's 1,900 groups include 450 multiple-choice groups. Following our protocol, these are posed as yes/no questions and count as correct when the model answers "No", so any reduction of "yes" confidence is rewarded on them. We therefore report the full benchmark (the paper's protocol) and the 1,450 binary groups, where a correct answer has its usual meaning. Values are joint accuracy (%).
The p-values compare our joint accuracy with each control: exact McNemar for the shift, and a permutation p over 500 draws for the shuffle. The shuffle keeps the damping and each item's own margin, and moves only δ between items.
We draw three conclusions, and the revised Sec. 6.4 reports both protocols and all controls.