incerto.sp.BaseSelectivePredictor

class incerto.sp.BaseSelectivePredictor(*args, **kwargs)

Bases: Module, ABC

Abstract base class for selective prediction methods.

Selective predictors enable models to abstain from predictions when uncertain, optimizing the risk-coverage tradeoff. This is crucial for safety-critical applications where wrong predictions are costly.

All selective predictors: 1. Generate logits via _forward_logits() 2. Compute confidence scores (default: max softmax probability) 3. Reject low-confidence predictions

Subclasses must implement _forward_logits() which defines how predictions are made (may include rejection mechanism in architecture).

Example

>>> class MySelectiveModel(BaseSelectivePredictor):
...     def __init__(self, backbone):
...         super().__init__()
...         self.backbone = backbone
...
...     def _forward_logits(self, x):
...         return self.backbone(x)
...
>>> model = MySelectiveModel(resnet)
>>> logits, conf = model(x, return_confidence=True)
>>> should_reject = model.reject(conf, threshold=0.9)
>>> # Make predictions only on high-confidence samples
>>> predictions = logits[~should_reject].argmax(dim=-1)

See also

• SoftmaxThreshold: Simple confidence thresholding

• SelfAdaptiveTraining: SAT with learned rejection

• DeepGambler: Gambler’s loss for selective classification

• SelectiveNet: Auxiliary selection head

Parameters:

• args (Any)

• kwargs (Any)

__init__(*args, **kwargs)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:

• args (Any)

• kwargs (Any)

Methods

__init__(*args, **kwargs)	Initialize internal Module state, shared by both nn.Module and ScriptModule.
add_module(name, module)	Add a child module to the current module.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
confidence_from_logits(logits)	Extract confidence scores from logits.
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(x, *[, return_confidence])	Forward pass with optional confidence scores.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
modules()	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
reject(confidence, threshold)	Determine which samples should be rejected based on confidence.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module[, strict])	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

Attributes

T_destination
call_super_init
dump_patches
training

forward(x, *, return_confidence=False)

Forward pass with optional confidence scores.

Parameters:

• x (Tensor) – Input tensor of shape (batch_size, *input_dims)

• return_confidence (bool) – If True, return (logits, confidence) tuple. If False, return only logits.

Returns:

logits tensor If return_confidence=True: (logits, confidence) tuple

Return type:

If return_confidence=False

Example

>>> logits = model(x)  # Just predictions
>>> logits, conf = model(x, return_confidence=True)  # With confidence

static confidence_from_logits(logits)

Extract confidence scores from logits.

Default implementation uses maximum softmax probability (MSP). Subclasses can override for different confidence measures.

Parameters:

logits (Tensor) – Tensor of shape (batch_size, num_classes)

Return type:

Tensor

Returns:

Confidence scores of shape (batch_size,) in range [0, 1]

static reject(confidence, threshold)

Determine which samples should be rejected based on confidence.

Parameters:

• confidence (Tensor) – Confidence scores of shape (batch_size,)

• threshold (float) – Confidence threshold. Samples below this are rejected.

Return type:

Tensor

Returns:

Boolean tensor of shape (batch_size,) where True indicates the sample should be rejected (abstained).

Example

>>> conf = torch.tensor([0.95, 0.60, 0.85, 0.40])
>>> should_reject = BaseSelectivePredictor.reject(conf, threshold=0.7)
>>> should_reject
tensor([False, True, False, True])